© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5041
    Prev
    Next
    INDEX
    Explanations

    features related to audio devices and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows specific keywords or phrases

    np_acts-logits-general · gemini-2.0-flash

    suitable decoration package

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ••
    -0.69
    pushFollow
    -0.66
    }*/
    
    -0.65
    GraphicsUnit
    -0.65
    —“
    -0.64
     Besøkt
    -0.64
    ,’”
    -0.63
     “…
    -0.63
    ….”
    -0.62
    …”
    -0.62
    POSITIVE LOGITS
     Suitable
    0.68
     Widely
    0.68
     decoration
    0.63
    ,
    0.62
     Decoration
    0.61
    Suitable
    0.61
     Exquisite
    0.59
    Package
    0.58
     ,
    0.57
     suitable
    0.56
    Activations Density 0.052%

    No Known Activations